检索结果-内蒙古大学图书馆

graph convolutional Enhanced Discriminative Broad Learning System for Hyperspectral Image Classification

IEEE ACCESS 2022年 10卷 90299-90311页

作者： Tuya Inner Mongolia Minzu Univ Coll Comp Sci & Technol Tongliao 028043 Peoples R China

Recently, broad learning system (BLS) have demonstrated excellent performance in hyperspectral images (HSI) classification. However, due to the complex geometric structure and spatial layout of HSI, the linear sparse features in broad learning system are difficult to fully represent hyperspectral data. In addition, the features learned by broad learning system lack more effective discriminative ability, which leads to the limited expressive ability of features. To address the issues, we propose a graph convolutional enhanced discriminative broad learning system (GCDBLS) for HSI Classification. GCDBLS aggregates the node information in the adjacency graph through graph convolution, and then learns the context relationship, so as to obtain rich nonlinear spatial spectral features in hyperspectral images;In order to extract more discriminative hyperspectral image features, GCDBLS introduces the concept of local intra-class scatter and local inter-class scatter. By minimizing the local intra-class feature distance and maximizing the local inter-class feature distance, GCDBLS can improve the discrimination ability of BLS extracted features. On three HSI datasets, the experiments compared with the latest classification methods show that the proposed method achieves good results, and improves the classification performance of hyperspectral images.

关键词： Feature extraction Hyperspectral imaging Convolution Learning systems Data mining Training data Deep learning convolutional neural networks Broad learning system hyperspectral image graph convolutional intra-class feature distance inter-class feature distance

来源：评论

学校读者我要写书评

暂无评论

AST-GCN: Augmented Spatial Temporal graph convolutional Neural Network for Gait Emotion Recognition

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第6期34卷 4581-4595页

作者： Chen, Chuang Sun, Xiao Tu, Zhengzheng Wang, Meng Anhui Univ Sch Artificial Intelligence Hefei 230601 Peoples R China Inst Artificial Intelligence Hefei Comprehens Natl Sci Ctr Hefei 230088 Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Anhui Prov Key Lab Affect Comp & Adv Intelligent M Hefei 230009 Peoples R China Anhui Univ Sch Comp Sci & Technol Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ Hefei 230009 Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230009 Peoples R China

Skeleton-based methods have recently achieved good performance in deep learning-based gait emotion recognition (DL-GER). However, the current methods have two drawbacks that limit the ability to learn discriminative emotional features from gait. First, these methods do not exclude the effect of the subject's walking orientation on emotion classification. Second, they do not sufficiently learn the implicit connections between the joints during human walking. In this paper, an augmented spatial-temporal graph convolutional neural network (AST-GCN) is introduced to solve these two problems. The interframe shift encoding (ISE) module acquires interframe shifts of joints to make the network sensitive to changes in emotion-related joint movements regardless of the subject's walking orientation. A multichannel implicit connection inference method learns more implicit connection relations related to emotions. Notably, we unify current skeleton-based methods into a common framework that validates the most powerful feature representation capability of our AST-GCN from a theoretical perspective. In addition, we extend the skeleton-based gait dataset using posture estimation software. Experiments demonstrate that our AST-GCN outperforms state-of-the-art methods on three datasets on two tasks.

关键词： Feature extraction Emotion recognition Legged locomotion Three-dimensional displays convolutional neural networks Pedestrians Support vector machines Gait emotion recognition graph convolutional affective computing

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Action Segmentation With Multi-Stage Spatial-Temporal graph convolutional Neural Networks

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING 2024年第1期12卷 202-212页

作者： Filtjens, Benjamin Vanrumste, Bart Slaets, Peter Katholieke Univ Leuven Dept Mech Engn B-3001 Leuven Belgium Katholieke Univ Leuven Dept Elect Engn ESAT B-3001 Leuven Belgium Katholieke Univ Leuven Dept Elect Engn ESAT B-3001 Leuven Belgium

The ability to identify and temporally segment fine-grained actions in motion capture sequences is crucial for applications in human movement analysis. Motion capture is typically performed with optical or inertial measurement systems, which encode human movement as a time series of human joint locations and orientations or their higher-order representations. State-of-the-art action segmentation approaches use multiple stages of temporal convolutions. The main idea is to generate an initial prediction with several layers of temporal convolutions and refine these predictions over multiple stages, also with temporal convolutions. Although these approaches capture long-term temporal patterns, the initial predictions do not adequately consider the spatial hierarchy among the human joints. To address this limitation, we recently introduced multi-stage spatial-temporal graph convolutional neural networks (MS-GCN). Our framework replaces the initial stage of temporal convolutions with spatial graph convolutions and dilated temporal convolutions, which better exploit the spatial configuration of the joints and their long-term temporal dynamics. Our framework was compared to four strong baselines on five tasks. Experimental results demonstrate that our framework is a strong baseline for skeleton-based action segmentation.

关键词： Activity segmentation activity detection dense labelling freezing of gait graph convolutional MS-GCN multi-stage spatial-temporal

来源：评论

学校读者我要写书评

暂无评论

Relation-consistency graph convolutional network for image super-resolution

引用

VISUAL COMPUTER 2024年第2期40卷 619-635页

作者： Yang, Yue Qi, Yong Qi, Saiyu Xi An Jiao Tong Univ Sch Comp Sci & Technol Xian Shaanxi Peoples R China

convolutional neural networks (CNNs) have been widely exploited in single image super-resolution (SISR) due to their powerful feature representation and the end-to-end training paradigm. Recent CNN-based SISR methods employ attention mechanism to enrich the feature representation and achieve notable performance. However, most of them use attention mechanism to model channel-wise dependencies, and the global relations of image features are not fully explored, thus hindering the discriminative learning capability. To amplify the feature representation, we propose a relation-consistency graph convolutional network (RGCN) for high-quality image rendering. Specifically, we introduce a spatial graph attention (SGA) to encode feature correlations in spatial dimension. Within SGA, the parameter-free Gram matrix is adopted to construct the global dependencies of pixel features, which dynamically measure the pixel-wise spatial relation. Furthermore, we embed a spatial pyramid pooling scheme into SGA to reduce the high complexity of correlation modeling between two pixels. Such an operation efficiently constructs the spatial relations through pixel and region-pooled features. Moreover, we propose a relation-consistency loss to retain the invariant of global relationship across all feature layers. The proposed loss regularizes the consistency between the low-resolution input and its corresponding high-resolution output in terms of the spatial relationships, enabling our network to learn a reasonable mapping and reconstruct more realistic images. Qualitative and quantitative comparison against state-of-the-art SISR methods on benchmark datasets under various degradation models demonstrate the superior performance of our RGCN.

关键词： Image super-resolution graph convolutional Attention mechanism Gram matrix

来源：评论

学校读者我要写书评

暂无评论

Local Discriminative Embedding Broad Learning System With graph convolutional for Hyperspectral Image Classification

引用

IEEE ACCESS 2023年 11卷 91879-91890页

作者： Li, Wei Shi, Yuanquan Li, Liyun Ma, Xiangbo Huaihua Univ Coll Comp & Artificial Intelligence Huaihua 418000 Hunan Peoples R China Beijing Wanweisheng New Technol Co Ltd Beijing 102200 Peoples R China

Broad learning system has attracted increasing attention in the hyperspectral image (HSI) classification, due to its universal approximation capability and high efficiency. However, two main challenges remained. One is that the mapping from the original BLS input to the mapped feature (MF) is linear, which is difficult to fully represent the complex spatial-spectral features of HSI. The other is that BLS fails to explore the local geometric structure relationship between samples within HSI. To overcome the limitations mentioned above, we propose a local discriminative embedding broad learning system with graph convolutional (GDEBLS). To address the first challenge, GDEBLS utilizes the graph convolution operation to aggregate the node information in the adjacent graph to learn the context and obtain the rich nonlinear spatial-spectral features in HSI. To deal with the second challenge, our method utilizes a neighborhood selection approach based on manifold structure to calculate the true distances between samples in the manifold space, overcoming the limitations of Euclidean distance measurement. Next, We introduce local manifold structure and discriminative information into BLS. The experimental results show that the proposed method significantly surpasses other state-of-the-art methods.

关键词： & nbsp Broad learning systems hyperspectral image local geometric structure graph convolutional

来源：评论

学校读者我要写书评

暂无评论

MC-GCN: A Multi-Scale Contrastive graph convolutional Network for Unconstrained Face Recognition With Image Sets

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 3046-3055页

作者： Shi, Xiao Chai, Xiujuan Xie, Jiake Sun, Tan Chinese Acad Agr Sci Agr Informat Inst Beijing 100081 Peoples R China Minist Agr & Rural Affairs Key Lab Agr Big Data Beijing 100081 Peoples R China Hangzhou Wangdao Holdings Co Ltd Hangzhou 310051 Peoples R China

In this paper, a Multi-scale Contrastive graph convolutional Network (MC-GCN) method is proposed for unconstrained face recognition with image sets, which takes a set of media (orderless images and videos) as a face subject instead of single media (an image or video). Due to factors such as illumination, posture, media source, etc., there are huge intra-set variances in a face set, and the importance of different face prototypes varies considerably. How to model the attention mechanism according to the relationship between prototypes or images in a set is the main content of this paper. In this work, we formulate a framework based on graph convolutional network (GCN), which considers face prototypes as nodes to build relations. Specifically, we first present a multi-scale graph module to learn the relationship between prototypes at multiple scales. Moreover, a Contrastive graph convolutional (CGC) block is introduced to build attention control model, which focuses on those frames with similar prototypes (contrastive information) between pair of sets instead of simply evaluating the frame quality. The experiments on IJB-A, YouTube Face, and an animal face dataset clearly demonstrate that our proposed MC-GCN outperforms the state-of-the-art methods significantly.

关键词： Prototypes Face recognition Feature extraction Semantics Faces Task analysis Media Face recognition image set graph convolutional contrastive information multi-scale

来源：评论

学校读者我要写书评

暂无评论

STA-GCN:Spatial Temporal Adaptive graph convolutional Network for Gait Emotion Recognition

STA-GCN:Spatial Temporal Adaptive Graph Convolutional Networ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chen, Chuang Sun, Xiao Anhui Univ AI Joint Lab IAI Hefei Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei Peoples R China

ISBN: (纸本)9781665468916

graph convolutional Neural Networks (GCNs) recently have been widely used in Gait Emotion Recognition (GER). However, the existing GCNs-based GER methods have two drawbacks that limit the ability to learn discriminative feature. In spatial modeling, context-sensitive affective feature of joint is under-extracted due to the neglect of implicit connection. In temporal modeling, multi-scale temporal feature of joint motion is under-extracted or aggregated rigidly. In this paper, we propose a novel Spatial-Temporal Adaptive graph convolutional Network (STA-GCN) where two main modules are introduced, respectively. Spatial Feature Learning Module (SFLM) infers context-sensitive joint implicit connection and adaptively aggregates spatial feature mined from implicit and explicit connection. Temporal Feature Learning Module (TFLM) extracts and adaptively aggregates multi-scale temporal feature of joint motion. It is worth mentioning that we first pre-train the model using hand-crafted affective feature and counterpart gait. Experimental results demonstrate our STA-GCN outperforms state-of-the-art methods in two tasks.

关键词： Gait Emotion Recognition graph convolutional Transfer Learning Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

graph convolutional Multi-modal Hashing for Flexible Multimedia Retrieval 21

Graph Convolutional Multi-modal Hashing for Flexible Multime...

引用

29th ACM International Conference on Multimedia (MM)

作者： Lu, Xu Zhu, Lei Liu, Li Nie, Liqiang Zhang, Huaxiang Shandong Normal Univ Jinan Shandong Peoples R China Shandong Univ Qingdao Shandong Peoples R China

ISBN: (纸本)9781450386517

Multi-modal hashing makes an important contribution to multimedia retrieval, where a key challenge is to encode heterogeneous modalities into compact hash codes. To solve this dilemma, graph-based multi-modal hashing methods generally define individual affinity matrix of each independent modality and apply linear algorithm for heterogeneous modalities fusion and compact hash learning. Several other methods construct graph Laplacian matrix based on semantic information to help learn discriminative hash code. However, these conventional methods roughly ignore the structural similarity of training set and the complex relations among multi-modal samples, which leads to unsatisfactory complementarity of fused hash codes. More notably, they are faced with two other important problems: huge computing and storage costs caused by graph construction and partial modality feature lost problem when incomplete query sample comes. In this paper, we propose a Flexible graph convolutional Multi-modal Hashing (FGCMH) method that adopts GCNs with linear complexity to preserve both the modality-individual and modality-fused structural similarity for discriminative hash learning. Necessarily, accurate multimedia retrieval can be performed on complete and incomplete datasets with our method. Specifically, multiple modality-individual GCNs under semantic guidance are proposed to act on each individual modality independently for intra-modality similarity preserving, then the output representations are fused into a fusion graph with adaptive weighting scheme. Hash GCN and semantic GCN, which share parameters in the first two layers, propagate fusion information and generate hash codes under high-level label space supervision. In the query stage, our method adaptively captures various multi-modal contents in a flexible and robust way, even if partial modality features are lost. Experimental results on three publicly datasets show the flexibility and effectiveness of our proposed method.

关键词： Hashing multi-modal multimedia retrieval graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Fast 3D-graph convolutional networks for skeleton-based action recognition

引用

APPLIED SOFT COMPUTING 2023年 145卷

作者： Zhang, Guohao Wen, Shuhuan Li, Jiaqi Che, Haijun Yanshan Univ Dept Key Lab Ind Comp Control Engn Hebei Prov Qinhuangdao 066004 Peoples R China

Research on human action recognition based on skeletons has received much attention. But most of the research focuses on improving the model's generalization ability, while ignoring significant efficiency issues. This leads to developing heavy models with poor scalability and cost-effectiveness in practical use. This paper, we investigate the under-studied but practically critical recognition model efficiency problem. To this end, we present a new Fast Recognition Distillation (FRD) model learning strategy. Specifically, FRD trains a lightweight recognition neural network structure that can be quickly executed at a low computational cost. It can be achieved by effectively disseminating the identification probability information of the teacher network to the lightweight network. We call the probability information of the teacher network as soft-target, and FRD can learn more potential information from soft-target. In addition, we also used a particular loss function for soft-target. Through the FRD network, while basically maintaining the recognition accuracy, we minimized the network structure. Extensive experiments on the two large-scale datasets, NTU-RGBD and Kinetics-Skeleton, demonstrate that our model (FRD) is more lightweight and refined than others. Therefore, our model FRD is efficient. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Action recognition Human skeleton graph convolutional Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

MULTIMODAL EMOTION RECOGNITION WITH CAPSULE graph convolutional BASED REPRESENTATION FUSION

MULTIMODAL EMOTION RECOGNITION WITH CAPSULE GRAPH CONVOLUTIO...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Liu, Jiaxing Chen, Sen Wang, Longbiao Liu, Zhilei Fu, Yahui Guo, Lili Dang, Jianwu Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Cognit Comp & Applicat Tianjin Peoples R China Japan Adv Inst Sci & Technol Nomi Ishikawa Japan Pengcheng Lab Shenzhen Peoples R China

ISBN: (纸本)9781728176055

Due to the more robust characteristics compared to unimodal, audio-video multimodal emotion recognition (MER) has attracted a lot of attention. The efficiency of representation fusion algorithm often determines the performance of MER. Although there are many fusion algorithms, information redundancy and information complementarity are usually ignored. In this paper, we propose a novel representation fusion method, Capsule graph convolutional Network (CapsGCN). Firstly, after unimodal representation learning, the extracted audio and video representations are distilled by capsule network and encapsulated into multimodal capsules respectively. Multimodal capsules can effectively reduce data redundancy by the dynamic routing algorithm. Secondly, the multimodal capsules with their inter-relations and intra-relations are treated as a graph structure. The graph structure is learned by graph convolutional Network (GCN) to get hidden representation which is a good supplement for information complementarity. Finally, the multimodal capsules and hidden relational representation learned by CapsGCN are fed to multihead self-attention to balance the contributions of source representation and relational representation. To verify the performance, visualization of representation, the results of commonly used fusion methods, and ablation studies of the proposed CapsGCN are provided. Our proposed fusion method achieves 80.83% accuracy and 80.23% F1 score on eNTERFACE05'.

关键词： multimodal emotion recognition capsule networks graph convolutional VGG-16

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：